首页> 外文会议>ASEE Annual Conference & Exposition;American Society for Engineering Education Annual Conference & Exposition >Segmentation Technique for the Learning in Recognition of the TwoHandwritten Bangla Digits Using Counterpropagation Neural Network
【24h】

Segmentation Technique for the Learning in Recognition of the TwoHandwritten Bangla Digits Using Counterpropagation Neural Network

机译:反向传播神经网络用于识别孟加拉手写体数字的学习的分割技术

获取原文

摘要

We are proposing a segmentation technique for the learning of the two Bangla digitsincorporating the grid method, the regional search method, the feature extraction method, and thecounterpropagation neural network. We emphasized the recognition of the two Bangla digits oneand nine since these two digits look similar. The experimental result shows an overall increasedrate of recognition for Bangla one and nine.
机译:我们提出一种分割技术,结合网格方法,区域搜索方法,特征提取方法和对向传播神经网络来学习两个孟加拉数字。我们强调了对孟加拉数字1和9的识别,因为这两个数字看起来很相似。实验结果表明,孟加拉一号和九号的识别率总体提高。

著录项

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号